Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Hasan Toor ✪

@hasantoxr

Oct 6 • 14 tweets • 5 min read • Read on X

Scrolly

12 GitHub repos that will help you start a career in AI engineering (100% free):

1. AI for Beginners by Microsoft

This repo includes topics like neural networks, language processing, computer vision, and more.

It's easy for beginners, focuses on projects, and includes real-world examples.

Check this👇

2. ML for Beginners by Microsoft

A 12-week program where you learn classical machine learning with real-world data using Scikit-learn.

It has quizzes, lessons in R and Python, and hands-on projects. Some lessons are available as short videos.

Check this👇

3. Awesome Generative AI

Generative AI is really popular right now, with uses like making images and understanding language.

This collection has a big list of resources on generative models like transformers, GANs, and diffusion models.

4. Hands-on LLMs

This is a detailed resource that will teach you about large language models, including tokenization, fine-tuning, and more.

Check this👇

5. Advanced RAG Techniques

This repository includes over 30 methods to make RAG systems quicker, smarter, and more accurate, such as HyDE, GraphRAG, and Vision RAG.

Check this 👇

6. AI Agents for Beginners by Microsoft

This course helps you learn how to create AI agents on your own using tools like Semantic Kernel, AutoGen, and MCP.

Check this👇

7. Agents Towards Production

This guide shows how to create GenAI agents, including tips on memory, organization, deployment, security, and more.

Check this 👇

8. DL Paper Implementations

This repository includes easy-to-understand PyTorch versions of over 60 research papers on topics like Transformers, GANs, and Diffusion models.

Check this👇

9. AI Engineering Hub

To really understand LLMs, RAG, and AI agents, you need hands-on projects.

AI Engineering Hub offers over 70 real-world examples, tutorials, and agent applications that you can build, adjust, and use.

Check this 👇

10. Neural Networks: Zero to Hero

This repository by Andrej Karpathy is a practical course where you learn to build modern deep learning systems from the ground up, including GPTs.

Check this 👇

11. FastAI

A Hands on Introduction to Deep Learning

The FastAI "fastbook" is a set of Jupyter Notebooks that teaches you about deep learning.

These important machine learning ideas can be learned using FastAI, which is based on PyTorch.

12. Made With ML

Learn how to use machine learning and software engineering to create, build, and improve real-world ML applications.

You'll find out how to take an idea and make it real by understanding data, training models, testing, and showing your work.

https://twitter.com/1506055005992026115/status/1975151893493232099

As always, Thank you for reading this.

If you enjoyed this post:

1. Follow me @hasantoxr for more of these
2. RT the tweet below to share this thread with your audience

https://twitter.com/1506055005992026115/status/1975151893493232099

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @hasantoxr

Hasan Toor ✪

@hasantoxr

Sep 29

Stanford just published research that destroys every prompt engineering guru.

Turns out most "advanced techniques" are just survivorship bias and confirmation bias.

Here's what the data actually shows:

The biggest lie: "Be specific and detailed"

Stanford researchers tested 100,000 prompts across 12 different tasks.

Longer prompts performed WORSE 73% of the time.

The sweet spot? 15-25 tokens for simple tasks, 40-60 for complex reasoning.

"Few-shot examples always help" - Total bullshit.

MIT's recent study shows few-shot examples hurt performance on 60% of tasks.

Why? Models get anchored to your examples and miss edge cases.

Zero-shot with good instructions beats few-shot 8 times out of 10.

Read 16 tweets

Hasan Toor ✪

@hasantoxr

Sep 29

How to Build SaaS Apps with AI (No Manual Coding Needed):

With DeepAgent, you can make your own AI app easily!

DeepAgent isn’t just an AI builder it’s your backend, frontend, and dev team in one.

You can make an app in just a few minutes.

It creates the login, database, buttons, and lets apps talk to each other automatically.

Here are some crazy example of Apps created with DeepAgent:

1. You can build complex agents like a contract analyzer with DeepAgent.

Read 11 tweets

Hasan Toor ✪

@hasantoxr

Sep 28

This guy is genius.

Someone gave Claude 4 Sonnet one mega prompt and now it runs his entire marketing engine:

→ Research
→ SEO
→ Ad copy
→ Content
→ Strategy

Here’s the exact prompt (steal it):

The mega prompt:

Steal it:

"
Act as a full-stack AI marketing strategist for a startup preparing to launch a new product or service. You will handle market research, positioning, messaging, content creation, email copywriting, and SEO ideation.

{Describe your product or service here}
{Who is the product for? (demographics, psychographics, industry, etc.)}
{e.g. “generate leads,” “build awareness,” “launch product,” etc.}
{e.g. “casual and fun,” “bold and punchy,” “professional and clear”}

Given the product, target audience, and goal:

1. **Customer Insight & Research**
- Generate an Ideal Customer Profile (ICP)
- Identify key pain points, goals, and decision drivers
- Suggest 3 positioning angles to resonate with this audience

2. **Messaging & Conversion Copy**
- Write a hook-driven landing page (headline, subheadline, CTA section)
- Provide 3 viral headline variations
- Create a messaging matrix: [Pain Point → Promise → Proof → CTA]

3. **Content Creation**
- Generate a 7-day content plan (Twitter + LinkedIn)
- Include daily post titles, themes, and tone suggestions
- Add 1 short-form video concept if relevant

4. **Email Marketing**
- Write 3 cold email variations:
- Value-first pitch
- Problem-agitate-solution
- Case-study / social proof style

5. **SEO Strategy**
- Suggest 1 SEO topic cluster aligned with the product
- Provide 5 blog post titles that target mid-to-high intent keywords
- Recommend a pillar + supporting post structure

6. **Output Format**
- Use clear section headers (e.g. “ICP”, “Landing Page Copy”, “SEO Titles”)
- Use markdown formatting for readability
- Do **not** explain your reasoning — just give the final, polished outputs

This should be delivered as a comprehensive marketing kit, ready to deploy.

"

My input:

<product>AI-powered scheduling tool for solopreneurs</product>
<target_audience>Freelancers and solo founders aged 25–40 who struggle with time management</target_audience>
<goal>Generate leads for upcoming launch</goal>
<tone>Bold and punchy</tone>

Read 7 tweets

Hasan Toor ✪

@hasantoxr

Sep 27

I finally understand how large language models actually work

After reading the 2025 textbook “Foundations of LLMs”

It blew my mind and cleared up years of confusion

Here’s everything i learned (in plain english):

To understand LLMs, start with pre-training.

We don’t teach them specific tasks.

We flood them with raw text and let them discover patterns on their own.

This technique is called self-supervised learning and it’s the foundation of everything.

There are 3 ways to pre-train:

→ Unsupervised: No labels at all
→ Supervised: Classic labeled data
→ Self-supervised: Model creates its own labels (e.g., “guess the missing word”)

LLMs use #3 it scales like crazy and teaches them language from scratch.

Read 19 tweets

Hasan Toor ✪

@hasantoxr

Sep 26

After 2 years of using ChatGPT, I can say that it is the technology that has revolutionized my life the most, along with the Internet.

So here are 10 prompts that have transformed my day-to-day life and that could do the same for you:

1. Learn anything from a 20-year expert even if you're clueless

"Pretend you are an expert with 20 years of experience in {industry/topic}. Break down the core principles a total beginner must understand. Use analogies, step-by-step logic, and simplify everything like I’m 5."

2. Brutally honest thought partner to sharpen your thinking

"Act as my personal thought partner. I’ll describe {my idea/problem}, and I want you to question every assumption, point out blind spots, and help me evolve it into something 10x better."

Read 12 tweets

Hasan Toor ✪

@hasantoxr

Sep 22

🚨BREAKING: AI can now do the job of a whole trading team that costs $300,000.

It watches markets all day and night, uses plans, and works quicker than any person.

Here’s how it works👇

Introducing Intellectia - the AI platform to help you reach your investment goals!

With this AI Stock Picker, you can get daily tips on which stocks to trade.

- Tackle market challenges with our unbiased AI Stock Picker

Try free today at Try.intellectia.ai

1. DayTrading Center

You can unlock daily trading opportunities with real-time event-driven insights and technical signals.

You can access simplified, powerful tools for intraday bottom and top signals trade like a pro, effortlessly!